Industrial command and dispatch method and system based on large model and digital twinning

Abstract

The invention provides an industrial command and dispatch method and system based on a large model and digital twinning, and the method comprises the steps: obtaining the equipment operation state information and business information of a target factory area, and synchronizing the equipment operation state information and business information to a pre-constructed digital twinning model of the target factory area; pushing equipment operation state information and service information in the digital twin model to a pre-constructed large model for processing and analysis to obtain pre-alarm information of the abnormal event, and feeding back the pre-alarm information of the abnormal event output by the large model to the digital twin model; and generating a decision suggestion for the abnormal event based on the pre-alarm information of the abnormal event, and issuing a task work order to a corresponding execution department based on the decision suggestion. The problems existing in an existing command and dispatch system are solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of industrial command, and in particular to an industrial command scheduling method and system based on large models and digital twinning. BACKGROUND

[0002] Currently, although some solutions based on Internet of Things (IoT) technology and automation control systems have been used in the industrial field to improve work efficiency and safety, these systems often lack sufficient intelligence and flexibility. Existing command scheduling systems usually rely on fixed rules for operation and are difficult to adapt to complex and variable working environments. In addition, the handling of emergencies mainly relies on manual intervention, which is not only inefficient but also prone to misjudgment. SUMMARY

[0003] Therefore, the present application aims to provide an industrial command scheduling method and system based on large models and digital twinning to improve the problems existing in the prior art.

[0004] To achieve the above-mentioned purpose, the technical solution adopted by the present application is as follows: In a first aspect, the present application provides an industrial command scheduling method based on large models and digital twinning, comprising: obtaining equipment running state information and business information of a target factory area, and synchronizing the equipment running state information and business information to a pre-constructed digital twinning model of the target factory area; pushing the equipment running state information and business information in the digital twinning model to a pre-constructed large model for processing and analysis to obtain pre-warning information of an abnormal event, and feeding back the pre-warning information of the abnormal event output by the large model to the digital twinning model; generating a decision suggestion for the abnormal event based on the pre-warning information of the abnormal event, and issuing a task work order to the corresponding execution department based on the decision suggestion.

[0005] Optionally, pushing the equipment running state information and business information in the digital twinning model to the pre-constructed large model for processing and analysis to obtain the pre-warning information of the abnormal event comprises: inferring the trend of the equipment running state information and business information pushed multiple times by the large model to the digital twinning model to obtain an abnormal event; analyzing the cause of the abnormal event based on pre-constructed graph data to generate the pre-warning information of the abnormal event.

[0006] Optionally, the pre-alarm information of the abnormal event is used to generate a decision suggestion for the abnormal event, including: determining a scene type, a task level and an abnormal reason type of the abnormal event based on pre-configured scene and device information and the pre-alarm information of the abnormal event; generating a preliminary decision suggestion based on the scene type, the task level and the abnormal reason type of the abnormal event; binding the preliminary decision suggestion with a corresponding department to determine an executing department; and obtaining a target decision suggestion after the preliminary decision suggestion is confirmed or adjusted.

[0007] Optionally, the target decision suggestion is used to issue a task work order to the corresponding executing department, including: generating a scheduling task based on the target decision suggestion, and issuing the task work order to the executing department based on a workflow of the scheduling task.

[0008] Optionally, before the device running state information and the business information of the target factory area are obtained, the method further includes: obtaining historical device running state information and historical business information of the target factory area; and training a large model based on the historical device running state information and the historical business information by using a deep learning algorithm.

[0009] Optionally, after the device running state information and the business information are synchronized to the digital twin model of the target factory area, the method further includes: comparing the device running state information with a pre-set parameter range, and issuing an alarm signal based on a comparison result.

[0010] In a second aspect, the present application provides an industrial command and dispatching system based on a large model and a digital twin, including: a data acquisition module, configured to acquire device running state information and business information of a target factory area, and synchronize the device running state information and the business information to a pre-constructed digital twin model of the target factory area; a data analysis module, configured to push the device running state information and the business information in the digital twin model to a pre-constructed large model for processing and analysis, to obtain pre-alarm information of an abnormal event, and feed back the pre-alarm information of the abnormal event output by the large model to the digital twin model; and a decision module, configured to generate a decision suggestion for the abnormal event based on the pre-alarm information of the abnormal event, and issue a task work order to a corresponding executing department based on the decision suggestion.

[0011] Optionally, the data analysis module is specifically configured to: predict a trend of the device running state information and the business information pushed by the digital twin model multiple times through the large model, to obtain the abnormal event; and analyze a reason of the abnormal event based on pre-constructed graph data, to generate the pre-alarm information of the abnormal event.

[0012] In a third aspect, the present application provides an electronic device, including a processor and a memory, the memory storing computer executable instructions capable of being executed by the processor, and the processor executes the computer executable instructions to implement steps of the method of any one of the first aspect. In a third aspect, the present application provides an electronic device, including a processor and a memory, the memory storing computer executable instructions capable of being executed by the processor, and the processor executes the computer executable instructions to implement steps of the method of any one of the first aspect.

[0013] In a fourth aspect, the present application provides a computer readable storage medium, and the computer readable storage medium stores a computer program, and the computer program is run by a processor to execute the steps of the method of any one of the first aspect.

[0014] The present application has the following beneficial effects: The industrial command and dispatch method and system based on the large model and digital twinning provided by the present application first acquires the equipment running state information and business information of the target factory area, and synchronizes the equipment running state information and business information to the digital twinning model of the target factory area constructed in advance; then pushes the equipment running state information and business information in the digital twinning model to the large model constructed in advance for processing and analysis to obtain pre-warning information of abnormal events, and feeds back the pre-warning information of abnormal events output by the large model to the digital twinning model; finally, generates decision suggestions for abnormal events based on the pre-warning information of abnormal events, and issues task work orders to the corresponding execution departments based on the decision suggestions. The above method analyzes the production data pushed by the digital twinning model through the large model, predicts the development trend of the production process and potential abnormal events, and can generate corresponding decision suggestions according to the pre-warning information generated by the large model, and issues task work orders to the corresponding execution departments to complete the processing of abnormal events, thereby improving the processing efficiency and response speed of the whole command and dispatch system, and improving the problems existing in the existing command and dispatch system.

[0015] Other features and advantages of the present application will be set forth in the following description, and in part will become apparent to those skilled in the art from the description, or can be learned by practice of the present application. The objects and other advantages of the present application will be realized and achieved by the structure particularly pointed out in the description, claims and drawings.

[0016] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the following will be described in detail with reference to the preferred embodiments and the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the specific embodiments of the present application or the technical solutions in the prior art, the following will briefly introduce the drawings needed to be used in the specific embodiments or the prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0018] Figure 1 A flowchart of an industrial command and dispatch method based on a large model and digital twinning provided by an embodiment of the present application; Figure 2A schematic diagram of a command and dispatch system provided by an embodiment of the present application is shown in the figure. Figure 3 A flowchart of another industrial command and dispatch method based on large models and digital twinning provided by an embodiment of the present application is shown in the figure. Figure 4 A structural schematic diagram of an industrial command and dispatch system based on large models and digital twinning provided by an embodiment of the present application is shown in the figure. Figure 5 A structural schematic diagram of an electronic device provided by an embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0019] To make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions of the present application will be described below in connection with the accompanying drawings, obviously, the described embodiments are some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of protection of the present application.

[0020] At present, the existing command and dispatch system usually relies on fixed rules for operation, and it is difficult to adapt to complex and variable working environments; in addition, the handling of emergency events also mainly relies on manual intervention, which not only is inefficient, but also is prone to misjudgment. At the same time, although the digital twinning technology has shown great potential in simulation and simulation, it still faces problems such as data island, insufficient model accuracy, etc. in actual application.

[0021] Based on this, the industrial command and dispatch method and system based on large models and digital twinning provided by an embodiment of the present application can improve the problems existing in the existing command and dispatch system.

[0022] To facilitate understanding of the present embodiment, first, a method for industrial command and dispatch based on large models and digital twinning disclosed by the present embodiment will be described in detail, which is applied to command and dispatch systems in multiple field business scenarios such as real estate, production, health, safety, etc. The method can be executed by an electronic device, such as a smart phone, a computer, a tablet computer, etc.

[0023] Referring to Figure 1 The flowchart of the method for industrial command and dispatch based on large models and digital twinning is shown in the figure, which shows that the method mainly includes the following steps S101 to S103: Step S101: Obtain the equipment running state information and business information of the target factory area, and synchronize the equipment running state information and business information to the pre-constructed digital twinning model of the target factory area.

[0024] In an embodiment, the parameter information of the plant layout of the target plant and the internal production equipment thereof is collected in advance, a three-dimensional model (i.e., a digital twin model) of the target plant is constructed through a digital twin technology, thereby establishing a dynamic link between the physical plant and its virtual copy, so that any change occurring in the real world can be immediately reflected in the virtual environment. The entire plant layout and its internal operation can be intuitively presented through a three-dimensional graphical visualization interface, which facilitates the management personnel to check the specific situation at any time and make corresponding decisions. In the embodiment of the present application, augmented reality (AR) / virtual reality (VR) technology can also be used to provide more intuitive operation guidance and training environment for operators, thereby improving the work efficiency and safety of the operators.

[0025] In a specific implementation, the equipment running state information and the business information of the target plant, such as the equipment state, production data, rules, scheduling plan, enterprise production hardware list, etc., are collected in real time, and the equipment running state information and the business information are synchronized to the digital twin model of the target plant constructed in advance. Specifically, a timing update synchronization mechanism can be set to ensure that the data of the digital twin model is consistent with the entity system in real time. In the embodiment of the present application, the Internet of Things (IoT) and edge computing can be used to collect data, more sensors are deployed, and local data is processed by edge computing, so that the data transmission delay can be reduced while the reaction can be made quickly.

[0026] In addition, in the embodiment of the present application, the equipment running state information can be compared with the pre-set parameter range, and an alarm signal can be issued based on the comparison result. Specifically, if the equipment running state information exceeds the pre-set parameter range, an alarm signal is issued, thereby realizing real-time monitoring and early warning of the production equipment and process flow.

[0027] Step S102: The equipment running state information and the business information in the digital twin model are pushed to the pre-constructed large model for processing and analysis, the pre-alarm information of the abnormal event is obtained, and the pre-alarm information of the abnormal event output by the large model is fed back to the digital twin model.

[0028] In an embodiment, the digital twin model can push the equipment running state information and the business information to the large model through a timing script. After receiving the data pushed by the digital twin model, the large model can further speculate the development trend of the data, at the same time, the large model can call the atlas data to analyze the possible causes and the excluded causes of the current abnormal event, and return the pre-alarm information to the digital twin model in the form of pre-alarm. The large model can also use the pre-programmed knowledge base to make fault diagnosis and decision suggestion.

[0029] Based on this, in the embodiment of the application, when the device running state information and the business information in the digital twin model are pushed into the pre-constructed large model for processing and analysis to obtain the pre-alarm information of the abnormal event, the following methods can be used, including but not limited to: first, the large model is used to speculate the trend of the device running state information and the business information pushed multiple times by the digital twin model, to obtain the abnormal event; then, the pre-constructed graph data is used to analyze the cause of the abnormal event, to generate the pre-alarm information of the abnormal event. The graph data is constructed according to historical production data and historical abnormal events, and contains the relationship between the causes of abnormal events, devices, process flows, maintenance knowledge of devices, fault handling measures, etc.

[0030] Step S103: generating a decision suggestion for the abnormal event based on the pre-alarm information of the abnormal event, and issuing a task work order to the corresponding execution department based on the decision suggestion.

[0031] In an embodiment, the best operation suggestion can be automatically generated or some key actions (i.e., decision suggestions) can be directly executed by learning the historical data in combination with the pre-alarm information of the abnormal event, such as adjusting the production line speed to avoid the occurrence of bottleneck phenomenon. Then, a task work order can be issued to the corresponding department according to the decision suggestion, so that the staff of the department can timely handle the abnormal event.

[0032] The industrial command and dispatching method based on the large model and the digital twin provided in the embodiment of the application can analyze the production data pushed by the digital twin model through the large model, predict the development trend of the production process and potential abnormal events, and can generate a corresponding decision suggestion according to the pre-alarm information generated by the large model, issue a task work order to the corresponding execution department, and complete the handling of the abnormal event, thereby improving the overall processing efficiency and response speed of the command and dispatching system and improving the problems existing in the existing command and dispatching system.

[0033] In an embodiment, for the aforementioned step S103, i.e., when the decision suggestion for the abnormal event is generated based on the pre-alarm information of the abnormal event, the following methods can be used, including but not limited to: First, the scene type, task level and abnormal cause type of the abnormal event are determined based on the pre-configured scene and device information and the pre-alarm information of the abnormal event.

[0034] In specific implementation, the scene and device configuration can be performed in advance through the configuration module of the system, and the scene type can be configured according to the demand, wherein the scene type includes four large categories of production, coal quality, safety and electromechanical, and each large category includes small categories such as device monitoring and fault prediction; specific devices and scenes can also be associated to clearly define the abnormal cause type (such as device failure, efficiency optimization, etc.).

[0035] Based on this, in the embodiments of the present application, the pre-alarm information of the abnormal event can be matched with the pre-configured scene and device information to obtain the closest scene type, task level and abnormal reason type.

[0036] Then, a preliminary decision suggestion is generated based on the scene type, task level and abnormal reason type of the abnormal event.

[0037] In specific implementation, the preliminary decision suggestion or the pre-alarm information can be generated according to the matched scene type, task level and abnormal reason type of the abnormal event, combined with historical data.

[0038] Next, the preliminary decision suggestion is bound to the corresponding department to determine the executing department.

[0039] In specific implementation, according to the decision suggestion, the decision suggestion is bound to the department (entity department such as operation and maintenance department or virtual department such as cross-functional team) involved, which is determined as the executing department of the decision suggestion.

[0040] Finally, after the preliminary decision suggestion is confirmed or adjusted, the target decision suggestion is obtained.

[0041] In specific implementation, the final target decision suggestion can be obtained through secondary confirmation or adjustment of the preliminary decision suggestion by the user, and the alarm is pushed. The preliminary decision suggestion can also be confirmed or adjusted by a large model.

[0042] In one embodiment, for the aforementioned step S103, when the task order is issued to the corresponding executing department based on the decision suggestion, the following modes can be adopted, including but not limited to: a scheduling task is generated based on the target decision suggestion, and a task order is issued to the executing department based on the workflow of the scheduling task.

[0043] In specific implementation, the scheduling task is generated according to the finally generated target decision suggestion, and the scheduling task is classified according to the scene type and the task level (such as first level, second level and third level), and then the scheduling task is classified to the corresponding virtual department or entity department for execution. Specifically, an automatic or manual workflow can be started to execute the scheduling task, and the task execution result is fed back, the production data change is continuously monitored, and a new round of data synchronization and optimization cycle is triggered.

[0044] In the embodiments of the present application, through data driving, dynamic updating and multi-department cooperation, closed-loop management from physical entity to digital model is realized, and work order is automatically generated and issued to complete timely maintenance and maintenance of production equipment.

[0045] An embodiment of the present invention also provides a large-scale model training method, comprising: first, obtaining historical equipment operating status information and historical business information from a target plant; then, using a deep learning algorithm to train a large-scale model based on this historical equipment operating status information and historical business information. In specific implementations, a deep learning algorithm can be used to train a large-scale model in conjunction with this historical equipment operating status information and historical business information. The large-scale model can be used to process data streams from various sensors and perform complex computing tasks, such as fault prediction and resource allocation optimization.

[0046] For example, if the digital twin model indicates a sudden increase in coal load on the gangue conveyor but hasn't reached the system's lower alarm limit, it will proactively push multiple data updates to the large model. This data might include information such as the current sorting density and corresponding standard values. Based on these updates, the large model can further infer trends and, by accessing graph data, push both possible causes and possible solutions to the current phenomenon as early warnings to the command and dispatch system.

[0047] For ease of understanding, the present invention also provides an industrial command and dispatch system based on a large model and digital twins. Figure 2 As shown, the command and dispatch system, centered around intelligent system analysis and control, deploys a large model and a digital twin. The digital twin interacts with various data systems to synchronize production data in real time. The large model leverages data pushed by the digital twin to analyze production issues, coal quality issues, electromechanical issues, and safety monitoring issues. Plant workshops and departments can directly interact with the system, receiving notifications and inquiries.

[0048] Specifically, the core architecture of the command and dispatch system includes: (1) Large model integration: A large-scale pre-trained model trained using deep learning algorithms is used as the core engine to process data streams from various sensors and perform complex computing tasks such as fault prediction and resource allocation optimization. The system uses a large pre-trained model built using deep learning algorithms to process complex industrial data streams and provide intelligent fault prediction, resource optimization and other functions.

[0049] (2) Digital twin modeling: Establishing a dynamic link between the physical plant and its virtual counterpart allows any changes in the real world to be immediately reflected in the virtual environment, and vice versa. This system uses digital twin modeling and a synchronous update mechanism to achieve precise mapping and real-time data synchronization between the physical entity and the virtual model, ensuring that the status between the two remains consistent, providing an accurate basis for decision support.

[0050] (3) Intelligent decision support: Through learning from historical data, the system can automatically generate optimal operation recommendations or directly execute certain critical actions, such as adjusting production line speed to avoid bottlenecks.

[0051] The functional modules of the command and dispatch system include: (1) Real-time monitoring and early warning: Continuously collect equipment operating status information and issue warning signals by comparing with normal parameter ranges.

[0052] (2) Emergency plan generation: Develop detailed response strategies based on pre-set safety standards to ensure rapid initiation of appropriate rescue measures in case of unexpected events.

[0053] (3) Visual interface display: Use three-dimensional graphical interfaces to intuitively present the entire plant layout and internal operation conditions, facilitating managers to view specific situations and make corresponding decisions at any time.

[0054] The core of the above command and dispatch system is "intelligent analysis + intelligent control", responsible for centralized processing, analysis and decision-making of data, as well as coordination of interactions between modules. Main functions include: (1) User feedback and analysis: Collect and analyze user feedback data. (2) Push / pull / notify: According to the analysis results, push information, recommend content or send notifications to relevant modules or users. (3) Interaction with the system: Support two-way data interaction between users or other modules and the system.

[0055] Further, the data flow process of the above command and dispatch system includes: (1) Input data.

[0056] Specifically, the workshop and each department upload business data (such as equipment status, production data, etc.) to the hub system. User feedback is input through the "user feedback and analysis" module of the hub. And push data to the command hub's large model through the timing script.

[0057] (2) Intelligent analysis and processing.

[0058] Specifically, the hub system uses large models to integrate and analyze input data, generating decision recommendations or warning information.

[0059] (3) Output and interaction.

[0060] Specifically, the hub system distributes results to relevant modules or users through "push", "pull", "notify" and other functions. Users or modules can query data or submit requests through the "interaction with the system" function.

[0061] (4) Closed-loop control.

[0062] Specifically, each department adjusts business operations (such as the safety department starting an emergency plan) according to the instructions of the central system to form a closed-loop management.

[0063] The above system provided by the embodiment of the present application realizes centralized processing and real-time management and control of data through the intelligent hub, covers multiple field businesses such as real estate, production, health and safety, supports full-process automatic transfer from data input to analysis, decision-making and feedback, and improves the overall operation efficiency and response speed of the system.

[0064] For the above command and dispatch system, the embodiment of the present application further provides a command and dispatch process based on the system, as shown in Figure 3 As shown in the figure, multi-source data is integrated, basic data such as equipment running state information is pushed to the large model through digital twinning, and each department synchronously updates business information to the large model, including rules, scheduling plans, enterprise production hardware lists, etc. The large model uses the received data to further speculate the trend of the data, at the same time, the atlas data is called to return the data to the digital twinning data center in the form of pre-alarm together with the possible causes and excluded causes of the current phenomenon, and the digital twinning system decides whether to alarm.

[0065] The command and dispatch system determines the scene type, task level and abnormal reason type according to the pre-alarm information returned by the large model, and then generates a dispatch task to be sent to the corresponding virtual department or entity department for execution.

[0066] The above method provided by the embodiment of the present application can automatically learn and predict the change trend of the production process, discover potential risks in time, and quickly respond. The method combines AI large model technology and digital twinning concept to provide more accurate, efficient and safe management means for industrial production.

[0067] For the industrial command and dispatch method based on the large model and digital twinning provided by the foregoing embodiment, the embodiment of the present application further provides an industrial command and dispatch system based on the large model and digital twinning, as shown in Figure 4 As shown in the structure schematic diagram of an industrial command and dispatch system based on a large model and digital twinning, the system mainly includes the following parts: The data acquisition module 401 is used to acquire the equipment running state information and business information of the target factory area, and synchronously update the equipment running state information and business information to the digital twinning model of the target factory area constructed in advance.

[0068] The data analysis module 402 is used to push the equipment running state information and business information in the digital twinning model to the large model constructed in advance for processing and analysis, obtain pre-alarm information of abnormal events, and feed back the pre-alarm information of abnormal events output by the large model to the digital twinning model.

[0069] The decision module 403 is configured to generate a decision suggestion for the abnormal event based on the pre-warning information of the abnormal event, and issue a task order to a corresponding execution department based on the decision suggestion.

[0070] The industrial command and dispatch system based on the large model and the digital twin provided by the embodiment of the present application can analyze the production data pushed by the digital twin model through the large model, predict the development trend of the production process and potential abnormal events, and generate a corresponding decision suggestion according to the pre-warning information generated by the large model, and issue a task order to the corresponding execution department to complete the processing of the abnormal event, thereby improving the overall processing efficiency and response speed of the command and dispatch system and improving the problems existing in the existing command and dispatch system.

[0071] In an embodiment, the data analysis module 402 is specifically configured to: predict the trend of the equipment operation state information and the business information pushed by the digital twin model multiple times through the large model to obtain an abnormal event; analyze the cause of the abnormal event based on pre-constructed atlas data to generate pre-warning information of the abnormal event.

[0072] In an embodiment, the decision module 403 is specifically configured to: determine the scene type, task level and abnormal reason type of the abnormal event based on the pre-configured scene and equipment information and the pre-warning information of the abnormal event; generate a preliminary decision suggestion based on the scene type, task level and abnormal reason type of the abnormal event; bind the preliminary decision suggestion with a corresponding department to determine an execution department; and obtain a target decision suggestion after confirming or adjusting the preliminary decision suggestion.

[0073] In an embodiment, the decision module 403 is specifically configured to: generate a dispatch task based on the target decision suggestion, and issue a task order to the execution department based on the workflow of the dispatch task.

[0074] In an embodiment, the system further comprises a model training module configured to: obtain historical equipment operation state information and historical business information of a target factory area; and train a large model by using a deep learning algorithm based on the historical equipment operation state information and the historical business information.

[0075] In an embodiment, the system further comprises a warning module configured to: compare the equipment operation state information with a pre-set parameter range, and issue a warning signal based on a comparison result.

[0076] It should be noted that the system provided by the embodiment of the present application has the same implementation principle and technical effects as the foregoing method embodiments, and for brevity, the part not mentioned in the system embodiment can be referred to the corresponding content in the foregoing method embodiments.

[0077] The embodiment of the present application further provides an electronic device, and specifically, the electronic device comprises a processor and a storage device; the storage device stores a computer program, and the computer program performs the method according to any one of the above embodiments when the computer program is run by the processor.

[0078] Figure 5 A structural schematic diagram of an electronic device provided by the embodiment of the present application is shown in the figure, and the electronic device 100 comprises a processor 50, a memory 51, a bus 52 and a communication interface 53, the processor 50, the communication interface 53 and the memory 51 are connected through the bus 52; the processor 50 is used for executing an executable module stored in the memory 51, for example, a computer program.

[0079] The memory 51 can contain a high-speed random access memory (RAM), and can also contain a non-volatile memory, for example, at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 53 (which can be wired or wireless), and the Internet, a wide area network, a local area network, a metropolitan area network and the like can be used.

[0080] The bus 52 can be an ISA bus, a PCI bus or an EISA bus and the like. The bus can be divided into an address bus, a data bus, a control bus and the like. For the convenience of representation, Figure 5 only one bidirectional arrow is used in the figure, but it does not mean that there is only one bus or only one type of bus.

[0081] The memory 51 is used for storing a program, and the processor 50 executes the program after receiving an execution instruction; the method performed by the device defined by the flow process disclosed in any one of the above embodiments can be applied to the processor 50 or realized by the processor 50.

[0082] The processor 50 can be an integrated circuit chip with signal processing capability. In implementation, each step of the above method can be completed by integrated logic circuit of hardware in the processor 50 or by instructions in the form of software. The processor 50 described above can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component. Each method, step and logic block diagram disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as a hardware code processor for execution, or a combination of hardware and software modules in the code processor for execution. The software module can be located in a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium in the art. The storage medium is located in the memory 51, and the processor 50 reads the information in the memory 51, and combines the hardware to complete the steps of the above method.

[0083] The computer program product of the readable storage medium provided by the embodiments of the present application comprises a computer readable storage medium storing program codes, and the program codes comprise instructions for executing the method described in the foregoing method embodiments. For specific implementation, reference can be made to the foregoing method embodiments, which will not be described here.

[0084] If the functions are realized in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application or the parts of the present application that essentially contribute to the prior art or the parts of the technical solutions can be embodied in the form of software products. The computer software product is stored in a storage medium and includes instructions for making a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method described in the embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0085] Finally, it should be noted that: the above-described embodiments are only specific embodiments of the present application, which are used to illustrate the technical solutions of the present application, but not to limit them. The protection scope of the present application is not limited thereto. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily think of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed by the present application, or make equivalent replacements to some of the technical features. The modifications, changes or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An industrial command and dispatch method based on large models and digital twins, characterized by: include: Acquire equipment operation status information and business information of the target plant, and synchronize the equipment operation status information and the business information to a pre-built digital twin model of the target plant; Pushing the device operating status information and the business information in the digital twin model to a pre-built large model for processing and analysis to obtain early warning information of abnormal events, and feeding back the early warning information of the abnormal events output by the large model to the digital twin model; A decision suggestion for the abnormal event is generated based on the pre-warning information of the abnormal event, and a task work order is issued to a corresponding execution department based on the decision suggestion.

2. The method according to claim 1, characterized in that The device operating status information and business information in the digital twin model are pushed to the pre-built large model for processing and analysis to obtain early warning information of abnormal events, including: The trend of the device operation status information and business information pushed multiple times by the digital twin model is inferred by the large model to obtain abnormal events; The cause of the abnormal event is analyzed based on the pre-constructed graph data, and the early warning information of the abnormal event is generated.

3. The method according to claim 1, characterized in that Generating a decision suggestion for the abnormal event based on the pre-warning information of the abnormal event, including: Determining the scenario type, task level, and abnormal cause type of the abnormal event based on pre-configured scenario and device information and the pre-alarm information of the abnormal event; Generate preliminary decision suggestions based on the scenario type, task level and abnormal cause type of the abnormal event; Bind the preliminary decision suggestions to the corresponding departments and determine the execution departments; After confirming or adjusting the preliminary decision suggestion, a target decision suggestion is obtained.

4. The method according to claim 3, characterized in that Based on the decision suggestions, a task work order is issued to the corresponding execution department, including: A scheduling task is generated based on the target decision suggestion, and a task work order is issued to the execution department based on the workflow of the scheduling task.

5. The method according to claim 1, characterized in that Before obtaining the equipment operation status information and business information of the target factory, it also includes: Obtaining historical equipment operation status information and historical business information of the target plant; Based on the historical equipment operation status information and the historical business information, the large model is obtained by training using a deep learning algorithm.

6. The method according to claim 1, characterized in that After synchronizing the equipment operation status information and the business information to the pre-built digital twin model of the target plant, the method further includes: The equipment operation status information is compared with a preset parameter range, and an alarm signal is issued based on the comparison result.

7. An industrial command and dispatch system based on large models and digital twins, characterized by: include: A data acquisition module is used to obtain equipment operation status information and business information of the target plant area, and synchronize the equipment operation status information and the business information to a pre-built digital twin model of the target plant area; A data analysis module is used to push the device operation status information and the business information in the digital twin model to a pre-built large model for processing and analysis, obtain early warning information of abnormal events, and feed back the early warning information of the abnormal events output by the large model to the digital twin model; The decision module is used to generate a decision suggestion for the abnormal event based on the pre-warning information of the abnormal event, and issue a task work order to the corresponding execution department based on the decision suggestion.

8. The system according to claim 7, characterized in that The data analysis module is specifically used for: The trend of the device operation status information and business information pushed multiple times by the digital twin model is inferred by the large model to obtain abnormal events; The cause of the abnormal event is analyzed based on the pre-constructed graph data, and the early warning information of the abnormal event is generated.

9. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement the steps of the method according to any one of claims 1 to 6.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are executed.

Images